holyclaude-ai-workstation
Deploy a full AI coding workstation with Claude Code, web UI, headless browser, and 5 AI CLIs in a single Docker container
What this skill does
# HolyClaude AI Workstation
> Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection.
HolyClaude is a containerized AI development workstation that bundles Claude Code CLI, a CloudCLI web UI, Chromium headless browser with Playwright, 5 AI CLIs (Claude, Gemini, OpenAI Codex, Cursor, TaskMaster AI), and 50+ dev tools into a single Docker image. One `docker compose up` replaces hours of manual setup.
---
## Installation
### Prerequisites
- Docker + Docker Compose installed
- Existing Anthropic account (Max/Pro subscription or API key)
### Quick Start
```bash
mkdir holyclaude && cd holyclaude
```
Create `docker-compose.yaml`:
```yaml
services:
holyclaude:
image: CoderLuii/HolyClaude:latest
container_name: holyclaude
hostname: holyclaude
restart: unless-stopped
shm_size: 2g
ports:
- "3001:3001"
volumes:
- ./data/claude:/root/.claude
- ./data/config:/root/.config
- ./projects:/workspace
environment:
- PUID=1000
- PGID=1000
```
```bash
docker compose up -d
# Open http://localhost:3001
```
### Image Variants
```bash
# Full image — all tools pre-installed (recommended)
docker pull CoderLuii/HolyClaude:latest
# Slim image — smaller download, tools installed on demand
docker pull CoderLuii/HolyClaude:slim
# Pinned version for production stability
docker pull CoderLuii/HolyClaude:1.2.3
docker pull CoderLuii/HolyClaude:1.2.3-slim
```
---
## Full Docker Compose Configuration
```yaml
services:
holyclaude:
image: CoderLuii/HolyClaude:latest
container_name: holyclaude
hostname: holyclaude
restart: unless-stopped
shm_size: 2g # Required for Chromium
ports:
- "3001:3001" # CloudCLI web UI
volumes:
- ./data/claude:/root/.claude # Claude credentials & config (persisted)
- ./data/config:/root/.config # App config (persisted)
- ./projects:/workspace # Your project files
environment:
# User/group IDs (match host user to avoid permission issues)
- PUID=1000
- PGID=1000
# AI provider API keys (optional — can also set via web UI)
- ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}
- GEMINI_API_KEY=${GEMINI_API_KEY}
- OPENAI_API_KEY=${OPENAI_API_KEY}
- CURSOR_API_KEY=${CURSOR_API_KEY}
# NAS/SMB mount polling (enable if using Synology/QNAP)
- CHOKIDAR_USEPOLLING=true
# Notification webhooks (optional)
- DISCORD_WEBHOOK_URL=${DISCORD_WEBHOOK_URL}
- SLACK_WEBHOOK_URL=${SLACK_WEBHOOK_URL}
security_opt:
- seccomp:unconfined # Required for Chromium sandbox
```
### Environment Variable Reference
| Variable | Required | Description |
|---|---|---|
| `PUID` | Recommended | Host user ID (run `id -u` to find yours) |
| `PGID` | Recommended | Host group ID (run `id -g` to find yours) |
| `ANTHROPIC_API_KEY` | Optional | Anthropic API key (alternative to OAuth login) |
| `GEMINI_API_KEY` | Optional | Google AI API key for Gemini CLI |
| `OPENAI_API_KEY` | Optional | OpenAI API key for Codex CLI |
| `CURSOR_API_KEY` | Optional | Cursor API key |
| `CHOKIDAR_USEPOLLING` | NAS only | Set `true` for SMB/NFS mounts |
| `DISCORD_WEBHOOK_URL` | Optional | Discord notifications |
| `SLACK_WEBHOOK_URL` | Optional | Slack notifications |
---
## Authentication
### Method 1: OAuth (Claude Max/Pro Subscription)
1. Open `http://localhost:3001`
2. Create a CloudCLI account (10 seconds)
3. Sign in with your Anthropic account via OAuth
4. No API key needed — uses your existing subscription
### Method 2: API Key
```yaml
environment:
- ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}
```
Or paste the key directly in the CloudCLI web UI settings.
### Credential Persistence
Credentials are stored in the bind-mounted volume:
```
./data/claude/ → /root/.claude/
./data/config/ → /root/.config/
```
Credentials survive container restarts, updates, and recreation.
---
## Platform-Specific Configuration
### Linux (amd64/arm64) — Default
```yaml
# No extra config needed
shm_size: 2g
```
### macOS (Docker Desktop)
```yaml
# Works out of the box with Docker Desktop
shm_size: 2g
```
### Windows (WSL2 + Docker Desktop)
```yaml
# Requires WSL2 backend enabled in Docker Desktop
shm_size: 2g
```
### Synology / QNAP NAS
```yaml
environment:
- CHOKIDAR_USEPOLLING=true # Fixes file watching on SMB mounts
volumes:
- /volume1/docker/holyclaude/data/claude:/root/.claude
- /volume1/docker/holyclaude/projects:/workspace
```
### Kubernetes (ARM64 / Oracle Cloud Graviton)
```yaml
# arm64 image is published alongside amd64
image: CoderLuii/HolyClaude:latest # multi-arch manifest auto-selects correct arch
```
---
## What's Inside the Container
### AI CLIs
| CLI | Invocation | Key Provider |
|---|---|---|
| Claude Code | `claude` | Anthropic (`ANTHROPIC_API_KEY` or OAuth) |
| Gemini CLI | `gemini` | Google (`GEMINI_API_KEY`) |
| OpenAI Codex | `codex` | OpenAI (`OPENAI_API_KEY`) |
| Cursor | `cursor` | Cursor (`CURSOR_API_KEY`) |
| TaskMaster AI | `task-master` | Uses configured AI provider keys |
### Headless Browser Stack
- **Chromium** — pre-installed and configured
- **Xvfb** — virtual display on `:99`
- **Playwright** — configured and ready
- **Shared memory** — `shm_size: 2g` pre-configured (fixes the 64MB Docker default)
### Dev Tools (50+)
- **Languages**: Node.js, Python 3, TypeScript, Bun, Deno
- **Package managers**: npm, yarn, pnpm, pip, cargo
- **Database clients**: PostgreSQL, MySQL, SQLite, Redis CLI
- **Cloud CLIs**: AWS CLI, Google Cloud SDK, Azure CLI
- **Dev tools**: GitHub CLI (`gh`), Git, curl, jq, ripgrep, fd
- **Process manager**: s6-overlay (auto-restart, graceful shutdown)
---
## Working with Projects
### Mount your project directory
```yaml
volumes:
- ./projects:/workspace
# Or mount a specific project:
- /path/to/my-app:/workspace/my-app
```
### Inside the container
```bash
# Access the container shell
docker exec -it holyclaude bash
# Navigate to workspace
cd /workspace
# Run Claude Code directly
claude
# Run other AI CLIs
gemini
codex
```
---
## Playwright / Headless Browser Usage
Playwright is pre-configured. Use it from Claude Code tasks or directly:
```typescript
// playwright.config.ts — already works inside the container
import { defineConfig } from '@playwright/test';
export default defineConfig({
use: {
// Chromium is pre-installed, no download needed
browserName: 'chromium',
launchOptions: {
args: [
'--no-sandbox',
'--disable-setuid-sandbox',
'--disable-dev-shm-usage', // Use /tmp instead of /dev/shm
],
},
},
});
```
```typescript
// Direct Playwright usage inside container
import { chromium } from 'playwright';
const browser = await chromium.launch({
args: [
'--no-sandbox',
'--disable-setuid-sandbox',
'--disable-dev-shm-usage',
],
});
const page = await browser.newPage();
await page.goto('https://example.com');
const screenshot = await page.screenshot({ path: '/workspace/screenshot.png' });
await browser.close();
```
```bash
# Run Playwright tests inside container
docker exec -it holyclaude bash -c "cd /workspace && npx playwright test"
# Run with headed mode via Xvfb
docker exec -it holyclaude bash -c "DISPLAY=:99 npx playwright test --headed"
```
---
## Updating HolyClaude
```bash
# Pull latest image
docker compose pull
# Recreate container with new image (zero data loss — data is in bind mounts)
docker compose up -d
# Or explicit recreation
docker compose down && docker compose up -d
```
### Pinned Version Strategy
```yaml
# For production: pin to a specific version
image: CoderLuii/HolyClaude:1.2.3
# Update by changing the tag and running:
docker compose up -d
```
---
## Data & Persistence
```
holyclaude/
├── docker-compose.yaml
├── data/
│ ├── claude/ # Claude credentials, .claude.json, history
│ └── config/ # CloudCLI anRelated in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.